wbyc/terraform-datadog-old-monitors
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

MON-160 - AWS monitors updated

Browse Source
This commit is contained in:
Alexandre Gaillet 2018-04-26 17:47:47 +02:00 committed by Quentin Manfroi
parent 3f17c0215c
commit 3c3ce6b3ae
15 changed files with 123 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
cloud/aws/apigateway/README.md
View File

@ -35,14 +35,17 @@ Inputs
| http_4xx_requests_silenced | Groups to mute for API Gateway HTTP 4xx requests monitor | map | `<map>` | no |
| http_4xx_requests_threshold_critical | Maximum critical acceptable percent of 4xx errors | string | `30` | no |
| http_4xx_requests_threshold_warning | Maximum warning acceptable percent of 4xx errors | string | `15` | no |
| http_4xx_requests_timeframe | Monitor timeframe for API HTTP 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| http_5xx_requests_message | Custom message for API Gateway HTTP 5xx requests monitor | string | `` | no |
| http_5xx_requests_silenced | Groups to mute for API Gateway HTTP 5xx requests monitor | map | `<map>` | no |
| http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `20` | no |
| http_5xx_requests_threshold_warning | Maximum warning acceptable percent of 5xx errors | string | `10` | no |
| http_5xx_requests_timeframe | Monitor timeframe for API HTTP 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| latency_message | Custom message for API Gateway latency monitor | string | `` | no |
| latency_silenced | Groups to mute for API Gateway latency monitor | map | `<map>` | no |
| latency_threshold_critical | Alerting threshold in milliseconds | string | `800` | no |
| latency_threshold_warning | Warning threshold in milliseconds | string | `400` | no |
| latency_timeframe | Monitor timeframe for API latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| message | Message sent when a monitor is triggered | string | - | yes |
Related documentation

18
cloud/aws/apigateway/inputs.tf
View File

@ -33,6 +33,12 @@ variable "latency_message" {
default = ""
}
variable "latency_timeframe" {
description = "Monitor timeframe for API latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "latency_threshold_critical" {
default = 800
description = "Alerting threshold in milliseconds"
@ -59,6 +65,12 @@ variable "http_5xx_requests_message" {
default = ""
}
variable "http_5xx_requests_timeframe" {
description = "Monitor timeframe for API HTTP 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "http_5xx_requests_threshold_critical" {
default = 20
description = "Maximum critical acceptable percent of 5xx errors"
@ -85,6 +97,12 @@ variable "http_4xx_requests_message" {
default = ""
}
variable "http_4xx_requests_timeframe" {
description = "Monitor timeframe for API HTTP 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "http_4xx_requests_threshold_critical" {
default = 30
description = "Maximum critical acceptable percent of 4xx errors"

6
cloud/aws/apigateway/monitors-api.tf
View File

@ -5,7 +5,7 @@ resource "datadog_monitor" "API_Gateway_latency" {
message = "${coalesce(var.latency_message, var.message)}"
query = <<EOF
min(last_5m): (
min(${var.latency_timeframe}): (
min:aws.apigateway.latency{${var.filter_tags}} by {region,apiname}
) > ${var.latency_threshold_critical}
EOF
@ -36,7 +36,7 @@ resource "datadog_monitor" "API_http_5xx_errors_count" {
message = "${coalesce(var.http_5xx_requests_message, var.message)}"
query = <<EOF
min(last_5m): (
min(${var.http_5xx_requests_timeframe}): (
default(
min:aws.apigateway.5xxerror{${var.filter_tags}} by {region,apiname}.as_count() /
(min:aws.apigateway.count{${var.filter_tags}} by {region,apiname}.as_count() + ${var.artificial_requests_count}),
@ -70,7 +70,7 @@ resource "datadog_monitor" "API_http_4xx_errors_count" {
message = "${coalesce(var.http_4xx_requests_message, var.message)}"
query = <<EOF
min(last_5m): (
min(${var.http_4xx_requests_timeframe}): (
default(
min:aws.apigateway.4xxerror{${var.filter_tags}} by {region,apiname}.as_count() /
(min:aws.apigateway.count{${var.filter_tags}} by {region,apiname}.as_count() + ${var.artificial_requests_count}),

3
cloud/aws/elasticsearch/README.md
View File

@ -33,14 +33,17 @@ Inputs
| cpu_silenced | Groups to mute for ES cluster cpu monitor | map | `<map>` | no |
| cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no |
| cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no |
| cpu_timeframe | Monitor timeframe for ES cluster cpu [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| diskspace_message | Custom message for ES cluster diskspace monitor | string | `` | no |
| diskspace_silenced | Groups to mute for ES cluster diskspace monitor | map | `<map>` | no |
| diskspace_threshold_critical | Disk free space in percent (critical threshold) | string | `10` | no |
| diskspace_threshold_warning | Disk free space in percent (warning threshold) | string | `20` | no |
| diskspace_timeframe | Monitor timeframe for ES cluster diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| environment | Architecture Environment | string | - | yes |
| es_cluster_status_message | Custom message for ES cluster status monitor | string | `` | no |
| es_cluster_status_silenced | Groups to mute for ES cluster status monitor | map | `<map>` | no |
| es_cluster_status_timeframe | Monitor timeframe for ES cluster status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_30m` | no |
| es_cluster_volume_size | ElasticSearch Domain volume size (in GB) | string | - | yes |
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |

18
cloud/aws/elasticsearch/inputs.tf
View File

@ -38,6 +38,12 @@ variable "es_cluster_status_message" {
default = ""
}
variable "es_cluster_status_timeframe" {
description = "Monitor timeframe for ES cluster status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_30m"
}
variable "es_cluster_volume_size" {
description = "ElasticSearch Domain volume size (in GB)"
}
@ -54,6 +60,12 @@ variable "diskspace_message" {
default = ""
}
variable "diskspace_timeframe" {
description = "Monitor timeframe for ES cluster diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_15m"
}
variable "diskspace_threshold_warning" {
description = "Disk free space in percent (warning threshold)"
default = "20"
@ -76,6 +88,12 @@ variable "cpu_message" {
default = ""
}
variable "cpu_timeframe" {
description = "Monitor timeframe for ES cluster cpu [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_15m"
}
variable "cpu_threshold_warning" {
description = "CPU usage in percent (warning threshold)"
default = "80"

6
cloud/aws/elasticsearch/monitors-elasticsearch.tf
View File

@ -18,7 +18,7 @@ resource "datadog_monitor" "es_cluster_status" {
type = "metric alert"
query = <<EOF
max(last_30m): (
max(${var.es_cluster_status_timeframe}): (
avg:aws.es.cluster_statusred{${data.template_file.filter.rendered}} by {region,name} * 2 +
(avg:aws.es.cluster_statusyellow{${data.template_file.filter.rendered}} by {region,name} + 0.1)
) >= 2
@ -52,7 +52,7 @@ resource "datadog_monitor" "es_free_space_low" {
type = "metric alert"
query = <<EOF
avg(last_15m): (
avg(${var.diskspace_timeframe}): (
avg:aws.es.free_storage_space{${data.template_file.filter.rendered}} by {region,name} /
(${var.es_cluster_volume_size}*1000) * 100
) < ${var.diskspace_threshold_critical}
@ -86,7 +86,7 @@ resource "datadog_monitor" "es_cpu_90_15min" {
type = "metric alert"
query = <<EOF
avg(last_15m): (
avg(${var.cpu_timeframe}): (
avg:aws.es.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
) > ${var.cpu_threshold_critical}
EOF

9
cloud/aws/elb/README.md
View File

@ -30,32 +30,37 @@ Inputs
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| dd_aws_elb | # ELB | string | `disable` | no |
| artificial_requests_count | Number of false requests used to mitigate false positive in case of low trafic | string | `5` | no |
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| elb_4xx_message | Custom message for ELB 4xx errors monitor | string | `` | no |
| elb_4xx_silenced | Groups to mute for ELB 4xx errors monitor | map | `<map>` | no |
| elb_4xx_threshold_critical | loadbalancer 4xx critical threshold in percentage | string | `10` | no |
| elb_4xx_threshold_warning | loadbalancer 4xx warning threshold in percentage | string | `5` | no |
| elb_4xx_timeframe | Monitor timeframe for ELB 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| elb_5xx_message | Custom message for ELB 5xx errors monitor | string | `` | no |
| elb_5xx_silenced | Groups to mute for ELB 5xx errors monitor | map | `<map>` | no |
| elb_5xx_threshold_critical | loadbalancer 5xx critical threshold in percentage | string | `10` | no |
| elb_5xx_threshold_warning | loadbalancer 5xx warning threshold in percentage | string | `5` | no |
| elb_5xx_timeframe | Monitor timeframe for ELB 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| elb_backend_4xx_message | Custom message for ELB backend 4xx errors monitor | string | `` | no |
| elb_backend_4xx_silenced | Groups to mute for ELB backend 4xx errors monitor | map | `<map>` | no |
| elb_backend_4xx_threshold_critical | loadbalancer backend 4xx critical threshold in percentage | string | `10` | no |
| elb_backend_4xx_threshold_warning | loadbalancer backend 4xx warning threshold in percentage | string | `5` | no |
| elb_backend_4xx_timeframe | Monitor timeframe for ELB backend 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| elb_backend_5xx_message | Custom message for ELB backend 5xx errors monitor | string | `` | no |
| elb_backend_5xx_silenced | Groups to mute for ELB backend 5xx errors monitor | map | `<map>` | no |
| elb_backend_5xx_threshold_critical | loadbalancer backend 5xx critical threshold in percentage | string | `10` | no |
| elb_backend_5xx_threshold_warning | loadbalancer backend 5xx warning threshold in percentage | string | `5` | no |
| elb_backend_5xx_timeframe | Monitor timeframe for ELB backend 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| elb_backend_latency_critical | latency critical threshold in seconds | string | `5` | no |
| elb_backend_latency_message | Custom message for ELB backend latency monitor | string | `` | no |
| elb_backend_latency_silenced | Groups to mute for ELB backend latency monitor | map | `<map>` | no |
| elb_backend_latency_timeframe | Monitor timeframe for ELB backend latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| elb_backend_latency_warning | latency warning threshold in seconds | string | `1` | no |
| elb_no_healthy_instance_message | Custom message for ELB no healty instance monitor | string | `` | no |
| elb_no_healthy_instance_silenced | Groups to mute for ELB no healty instance monitor | map | `<map>` | no |
| elb_no_healthy_instance_timeframe | Monitor timeframe for ELB no healty instance [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| environment | Architecture Environment | string | - | yes |
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
| message | Message sent when an alert is triggered | string | - | yes |

40
cloud/aws/elb/inputs.tf
View File

@ -25,10 +25,6 @@ variable "filter_tags_custom" {
}
## ELB
variable "dd_aws_elb" {
default = "disable"
}
variable "elb_no_healthy_instance_silenced" {
description = "Groups to mute for ELB no healty instance monitor"
type = "map"
@ -41,6 +37,12 @@ variable "elb_no_healthy_instance_message" {
default = ""
}
variable "elb_no_healthy_instance_timeframe" {
description = "Monitor timeframe for ELB no healty instance [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "elb_4xx_silenced" {
description = "Groups to mute for ELB 4xx errors monitor"
type = "map"
@ -53,6 +55,12 @@ variable "elb_4xx_message" {
default = ""
}
variable "elb_4xx_timeframe" {
description = "Monitor timeframe for ELB 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "elb_4xx_threshold_warning" {
description = "loadbalancer 4xx warning threshold in percentage"
default = 5
@ -75,6 +83,12 @@ variable "elb_5xx_message" {
default = ""
}
variable "elb_5xx_timeframe" {
description = "Monitor timeframe for ELB 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "elb_5xx_threshold_warning" {
description = "loadbalancer 5xx warning threshold in percentage"
default = 5
@ -97,6 +111,12 @@ variable "elb_backend_4xx_message" {
default = ""
}
variable "elb_backend_4xx_timeframe" {
description = "Monitor timeframe for ELB backend 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "elb_backend_4xx_threshold_warning" {
description = "loadbalancer backend 4xx warning threshold in percentage"
default = 5
@ -119,6 +139,12 @@ variable "elb_backend_5xx_message" {
default = ""
}
variable "elb_backend_5xx_timeframe" {
description = "Monitor timeframe for ELB backend 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "elb_backend_5xx_threshold_warning" {
description = "loadbalancer backend 5xx warning threshold in percentage"
default = 5
@ -141,6 +167,12 @@ variable "elb_backend_latency_message" {
default = ""
}
variable "elb_backend_latency_timeframe" {
description = "Monitor timeframe for ELB backend latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "elb_backend_latency_warning" {
description = "latency warning threshold in seconds"
default = 1

12
cloud/aws/elb/monitors-elb.tf
View File

@ -11,7 +11,7 @@ resource "datadog_monitor" "ELB_no_healthy_instances" {
message = "${coalesce(var.elb_no_healthy_instance_message, var.message)}"
query = <<EOF
min(last_5m): (
min(${var.elb_no_healthy_instance_timeframe}): (
min:aws.elb.healthy_host_count{${data.template_file.filter.rendered}} by {region,loadbalancername}
) < 1
EOF
@ -38,7 +38,7 @@ resource "datadog_monitor" "ELB_too_much_4xx" {
message = "${coalesce(var.elb_4xx_message, var.message)}"
query = <<EOF
min(last_5m): (
min(${var.elb_4xx_timeframe}): (
default(
min:aws.elb.httpcode_elb_4xx{${data.template_file.filter.rendered}} by {region,loadbalancername}.as_count() /
(min:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername}.as_count() + ${var.artificial_requests_count}),
@ -73,7 +73,7 @@ resource "datadog_monitor" "ELB_too_much_5xx" {
message = "${coalesce(var.elb_5xx_message, var.message)}"
query = <<EOF
min(last_5m): (
min(${var.elb_5xx_timeframe}): (
default(
min:aws.elb.httpcode_elb_5xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(min:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
@ -108,7 +108,7 @@ resource "datadog_monitor" "ELB_too_much_4xx_backend" {
message = "${coalesce(var.elb_backend_4xx_message, var.message)}"
query = <<EOF
min(last_5m): (
min(${var.elb_backend_4xx_timeframe}): (
default(
min:aws.elb.httpcode_backend_4xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(min:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
@ -143,7 +143,7 @@ resource "datadog_monitor" "ELB_too_much_5xx_backend" {
message = "${coalesce(var.elb_backend_5xx_message, var.message)}"
query = <<EOF
min(last_5m): (
min(${var.elb_backend_5xx_timeframe}): (
default(
min:aws.elb.httpcode_backend_5xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(min:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
@ -178,7 +178,7 @@ resource "datadog_monitor" "ELB_backend_latency" {
message = "${coalesce(var.elb_backend_latency_message, var.message)}"
query = <<EOF
min(last_5m): (
min(${var.elb_backend_latency_warning}): (
min:aws.elb.latency{${data.template_file.filter.rendered}} by {region,loadbalancername}
) > ${var.elb_backend_latency_critical}
EOF

4
cloud/aws/rds/README.md
View File

@ -29,12 +29,14 @@ Inputs
| cpu_silenced | Groups to mute for RDS CPU usage monitor | map | `<map>` | no |
| cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no |
| cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no |
| cpu_timeframe | Monitor timeframe for RDS CPU usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| diskspace_message | Custom message for RDS free diskspace monitor | string | `` | no |
| diskspace_silenced | Groups to mute for RDS free diskspace monitor | map | `<map>` | no |
| diskspace_threshold_critical | Disk free space in percent (critical threshold) | string | `10` | no |
| diskspace_threshold_warning | Disk free space in percent (warning threshold) | string | `20` | no |
| diskspace_timeframe | Monitor timeframe for RDS free diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| environment | Architecture Environment | string | - | yes |
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
| message | Message sent when an alert is triggered | string | - | yes |

12
cloud/aws/rds/inputs.tf
View File

@ -38,6 +38,12 @@ variable "cpu_message" {
default = ""
}
variable "cpu_timeframe" {
description = "Monitor timeframe for RDS CPU usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_15m"
}
variable "cpu_threshold_warning" {
description = "CPU usage in percent (warning threshold)"
default = "80"
@ -60,6 +66,12 @@ variable "diskspace_message" {
default = ""
}
variable "diskspace_timeframe" {
description = "Monitor timeframe for RDS free diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_15m"
}
variable "diskspace_threshold_warning" {
description = "Disk free space in percent (warning threshold)"
default = "20"

4
cloud/aws/rds/monitors-rds.tf
View File

@ -14,7 +14,7 @@ resource "datadog_monitor" "rds_cpu_90_15min" {
type = "metric alert"
query = <<EOF
avg(last_15m): (
avg(${var.cpu_timeframe}): (
avg:aws.rds.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
) > ${var.cpu_threshold_critical}
EOF
@ -46,7 +46,7 @@ resource "datadog_monitor" "rds_free_space_low" {
type = "metric alert"
query = <<EOF
avg(last_15m): (
avg(${var.diskspace_timeframe}): (
avg:aws.rds.free_storage_space{${data.template_file.filter.rendered}} by {region,name} /
avg:aws.rds.total_storage_space{${data.template_file.filter.rendered}} by {region,name} * 100
) < ${var.diskspace_threshold_critical}

3
cloud/aws/vpn/README.md
View File

@ -24,10 +24,11 @@ Inputs
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| environment | Architecture Environment | string | - | yes |
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| environment | Architecture Environment | string | - | yes |
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
| message | Message sent when an alert is triggered | string | - | yes |
| vpn_status_message | Custom message for VPN status monitor | string | `` | no |
| vpn_status_silenced | Groups to mute for VPN status monitor | map | `<map>` | no |
| vpn_status_timeframe | Monitor timeframe for VPN status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |

6
cloud/aws/vpn/inputs.tf
View File

@ -35,3 +35,9 @@ variable "vpn_status_message" {
type = "string"
default = ""
}
variable "vpn_status_timeframe" {
description = "Monitor timeframe for VPN status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}

2
cloud/aws/vpn/monitors-vpn.tf
View File

@ -11,7 +11,7 @@ resource "datadog_monitor" "VPN_status" {
message = "${coalesce(var.vpn_status_message, var.message)}"
query = <<EOF
avg(last_5m): (
avg(${var.vpn_status_timeframe}): (
avg:aws.vpn.tunnel_state{${data.template_file.filter.rendered}} by {region,name}
) < 1
EOF